• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.278-287
• /
• 2019

Spatial information extraction is to retrieve static and dynamic aspects in natural language text by explicitly marking spatial elements and their relational words. This paper proposes a deep learning approach for spatial information extraction for Korean language using a two-step bidirectional LSTM-CRF ensemble model. The integrated model of spatial element extraction and spatial relation attribute extraction is proposed too. An experiment with the Korean SpaceBank demonstrates the better efficiency of the proposed deep learning model than that of the previous CRF model, also showing that the proposed ensemble model performed better than the single model.

• The Mathematical Education
• /
• v.52 no.2
• /
• pp.203-215
• /
• 2013

We explored implications of storytelling in learning and teaching mathematics and examined examples of storytelling for deep understanding of the educational meanings of storytelling and new direction of storytelling approach to mathematics teachers. Mathematics had been commonly considered as the subject irrelevant to the narrative mode of thinking and only relevant to the paradigmatic mode of thinking that has rigorous logical forms and independent from human mind. As a result, this common sense forced a transmission pedagogy of mathematics: only the teachers as owners of the objective and logical truth of mathematics could transmit mathematical truths to students. Storytelling is highlighted as an alternative to the common teaching practices of mathematics focused only on the paradigmatic mode of thinking. Although a lot of research about the educational uses of storytelling mainly focused on the development and modification of stories, we suggested that the educational interest about storytelling should move to the elements or techniques for the positive effect of storytelling.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1591-1598
• /
• 2008

Z. Cao had proposed NFRM(new fuzzy reasoning method) which infers in detail using relation matrix. In spite of the small inference rules, it shows good performance than mamdani's fuzzy inference method. In this paper, we propose Z. Cao's fuzzy inference method with learning ability which is used a gradient descent method in order to improve the performances. It is hard to determine the relation matrix elements by trial and error method. Because this method is needed many hours and effort. Simulation results are applied nonlinear systems show that the proposed inference method using a gradient descent method has good performances.

• Journal of Korean language education
• /
• v.29 no.3
• /
• pp.117-144
• /
• 2018

The purpose of this study is to explore the linguistic elements that can promote academic literacy in terms of content-based instructions for KSL learners. In order to study the characteristics of learning languages for subjects, focus was given to the framework of systematic functional linguistics that has been extensively used in ELL teaching and learning research in the United States and Australia. History, which is taught in all classes and classified as a required course, was the subject of analysis. From the history curriculum, the elementary school level texts "Social Studies 5-2" and "Social Studies 6-1" were chosen for the analysis. Based on the results, we can come to the following conclusions. First, history textbooks are divided into narrative and analytical explanatory sub-genres based on their content, and there are differences in the factors that need to be focused on to find the main information. Second, the vocabulary of history textbooks should focus on the use of verbs which comprehend material processes. Particularly, learners should pay attention to the differences in meaning between low-frequency expressions. We hope that the results of this study will have a positive effect on history subject learning for learners in the "Adaptive Korean Course" and will help establish direction in terms of building curriculum contents for KSL learners.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1621-1633
• /
• 2022

The present study aims to design an application for anger control training of individuals and test its practical usability with the goal of encouraging preventive training in daily life. This study also investigates, through usability evaluation, whether users can use the application to carry out the actual anger management training program, whether it is useful and convenient, and whether it produces adequate learning effects. In order to conduct usability evaluation, a usability evaluation scale comprised of six factors-utility, reuse intention, learning, error, and reflectivity-was derived, and survey items tailored to each factor were produced. The association between usability evaluation elements, user demographic parameters, mobile usage behavior, and state anger was also examined. The result demonstrated that additional menus and features are necessary to increase the usability of the application for anger management. The result also revealed that it is vital to build an intuitive application interface that users unfamiliar with mobile app functionality can easily navigate, as well as to add entertaining components in the content, as users may be somewhat bored. On the basis of the findings, ideas of modifying and creating anger management training programs were discussed.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.5
• /
• pp.547-553
• /
• 2021

Dynamic object recognition is an important task for autonomous vehicles. Since dynamic objects exhibit a higher collision risk than static objects, our own trajectories should be planned to match the future state of moving elements in the scene. Time information such as optical flow can be used to recognize movement. Existing optical flow calculations are based only on camera sensors and are prone to misunderstanding in low light conditions. In this regard, to improve recognition performance in low-light environments, we applied a normalization filter and a correction function for Gamma Value to the input images. The low light quality improvement algorithm can be applied to confirm the more accurate detection of Object's Bounding Box for the vehicle. It was confirmed that there is an important in object recognition through image prepocessing and deep learning using YOLO.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1119-1139
• /
• 2021

Among the scientific literature, it has not been possible to find a consensus on the definition of the limits or properties that allow differentiating or grouping the cyber-physical systems (CPS) and the Internet of Things (IoT). Despite this controversy the papers reviewed agree that both have become crucial elements not only for industry but also for society in general. The impact of a malware attack affecting one of these systems may suppose a risk for the industrial processes involved and perhaps also for society in general if the system affected is a critical infrastructure. This article reviews the state of the art of the application of machine learning in the automation of malware detection in cyberphysical systems, evaluating the most representative articles in this field and summarizing the results obtained, the most common malware attacks in this type of systems, the most promising algorithms for malware detection in cyberphysical systems and the future lines of research in this field with the greatest potential for the coming years.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.61-67
• /
• 2022

In this paper, we propose a model that can convert some of the simulation program resources to a mobile environment. Recently, smart factories that use PLCs as controllers in the manufacturing industry are rapidly becoming widespread. However, in the situation where it is difficult to operate due to the shortage of PLC operation personnel, the actual situation is that a platform for PLC operation education is necessary. Currently most PLC-related educational platforms are based on 2D, which makes accurate learning difficult and difficult. When a simulation program is applied to distance learning in a general PC environment, many elements are displayed on the monitor, which makes screen switching inconvenient. Experiments with the proposed model confirmed that there was no frame deterioration under general circumstances. The average response time by the request frame was 102 ms, and it was judged that the learner was not at the level of experiencing the system delay.

• Smart Media Journal
• /
• v.10 no.4
• /
• pp.80-90
• /
• 2021

Using optical music recognition technology based on deep learning, we propose to apply the results derived to VR games. To detect the music objects in the music sheet, the deep learning model used YOLO v5, and Hough transform was employed to detect undetected objects, modifying the size of the staff. It analyzes and uses BPM, maximum number of combos, and musical notes in VR games using output result files, and prevents the backlog of notes through Object Pooling technology for resource management. In this paper, VR games can be produced with music elements derived from optical music recognition technology to expand the utilization of optical music recognition along with providing VR contents.

• Nuclear Engineering and Technology
• /
• v.54 no.2
• /
• pp.644-652
• /
• 2022

During the pyroprocessing operation, various signals can be collected by process monitoring (PM). These signals are utilized to diagnose process states. In this study, feasibility of using PM for nuclear safeguards of electrorefining operation was examined based on the use of machine learning for detecting off-normal operations. The off-normal operation, in this study, is defined as co-deposition of key elements through reduction on cathode. The monitored process signal selected for PM was cathode potential. The necessary data were produced through electrodeposition experiments in a laboratory molten salt system. Model-based cathodic surface area data were also generated and used to support model development. Computer models for classification were developed using a series of recurrent neural network architectures. The concept of transfer learning was also employed by combining pre-training and fine-tuning to minimize data requirement for training. The resulting models were found to classify the normal and the off-normal operation states with a 95% accuracy. With the availability of more process data, the approach is expected to have higher reliability.